40 accepted papers
Video frame interpolation (VFI), which generates intermediate frames from given start and end frames, has become a fundamental function in video generation applications. However, existing generative VFI methods are constrained to synthesizing a fixed number of intermediate frames, lacking the flexib…
Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space without explicitly shaping its distribution, making it unclear wh…
We propose unsupervised multi-scenario (UMS) person re-identification (ReID) as a new task that expands ReID across diverse scenarios (cross-resolution, clothing change, etc.) within a single coherent framework. To tackle UMS-ReID, we introduce image-text knowledge modeling (ITKM) -- a three-stage f
Agent-based editing models have substantially advanced interactive experiences, processing quality, and creative flexibility. However, two critical challenges persist: (1) instruction hallucination--text-only chain-of-thought (CoT) reasoning cannot fully prevent factual errors due to inherent inform
CLIP is a seminal multimodal model that maps images and text into a shared representation space by contrastive learning on billions of image–caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate how the superior linguistic understanding and broad world knowled
Unified multi-modal understanding/generative models have shown improved image editing performance by incorporating fine-grained understanding into their Chain-of-Thought (CoT) process. However, a critical question remains underexplored: what forms of CoT and training strategy can jointly enhance bot
Recent text-to-image (T2I) diffusion models have achieved impressive progress in generating high-fidelity images, yet they often fail to faithfully follow complex user prompts, especially in attribute binding, negation, and compositional reasoning. To address this limitation, we propose PromptEnhanc
In-context image generation and editing (ICGE) enables users to specify visual concepts through interleaved image-text prompts, demanding precise understanding and faithful execution of user intent. Although recent unified multimodal models exhibit promising understanding capabilities, these strengt
Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise between conflicting objectives (e.g., local editing v.s. subject-driven generation). While the sparse Mixture-of-Experts (MoE
Color variations, a key challenge in the unsupervised visible-infrared person re-identification (UVI-ReID) task, have garnered significant attention. While existing UVI-ReID methods have made substantial efforts during the optimization phase to enhance the model's robustness to color variations, the…
Clothing change person re-identification (CC-ReID) aims to match different images of the same person, even when the clothing varies across images. To reduce manual labeling costs, existing unsupervised CC-ReID methods employ clustering algorithms to generate pseudo-labels. However, they often fail t…
Visible-infrared person re-identification (VI-ReID) aims to match visible and infrared images of the same individual. Supervised VI-ReID (SVI-ReID) methods have achieved promising performance under the guidance of manually annotated identity labels. However, the substantial annotation cost severely…
Recent advances in multimodal Reward Models (RMs) have shown significant promise in delivering reward signals to align vision models with human preferences. However, current RMs are generally restricted to providing direct responses or engaging in shallow reasoning processes with limited depth, ofte…
"Conventional text-to-motion generation methods are usually trained on limited text-motion pairs, making them hard to generalize to open-vocabulary scenarios. Some works use the CLIP model to align the motion space and the text space, aiming to enable motion generation from natural language motion d…
Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image. Previous methods have relied on domain-specific heuristics such as warping-based motion representation and 3D Morphable Models, which limit the naturalness and diversity of the ge…
We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling. Existing radiance representations either require an implicit feature decoder, which significantly degrades the modeling power of the representation, or are spatially…
We present MicroCinema a straightforward yet effective framework for high-quality and coherent text-to-video generation. Unlike existing approaches that align text prompts with video directly MicroCinema introduces a Divide-and-Conquer strategy which divides the text-to-video into a two-stage proces…
In this work we aim to improve the 3D reasoning ability of Transformers in multi-view 3D human pose estimation. Recent works have focused on end-to-end learning-based transformer designs which struggle to resolve geometric information accurately particularly during occlusion. Instead we propose a no…
We introduce a highly performant 3D object detector for point clouds using the DETR framework. The prior attempts all end up with suboptimal results because they fail to learn accurate inductive biases from the limited scale of training data. In particular, the queries often attend to points that ar…
Inspired by the success of volumetric 3D pose estimation, some recent human mesh estimators propose to estimate 3D skeletons as intermediate representations, from which, the dense 3D meshes are regressed by exploiting the mesh topology. However, body shape information is lost in extracting skeletons…
We introduce AiT, a unified output representation for various vision tasks, which is a crucial step towards general-purpose vision task solvers. Despite the challenges posed by the high-dimensional and task-specific outputs, we showcase the potential of using discrete representation (VQ-VAE) to mode…
Human pose is typically represented by a coordinate vector of body joints or their heatmap embeddings. While easy for data processing, unrealistic pose estimates are admitted due to the lack of dependency modeling between the body joints. In this paper, we present a structured representation, named…
Robustness and discrimination power are two fundamental requirements in visual object tracking. In most tracking paradigms, we find that the features extracted by the popular Siamese-like networks can not fully discriminatively model the tracked targets and distractor objects, hindering them from si…
"While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes. We present Faster VoxelPose to address the challenge by re-projecting the feature volume to the three two-di…
"As an important upstream task for many medical applications, supervised landmark localization still requires non-negligible annotation costs to achieve desirable performance. Besides, due to cumbersome collection procedures, the limited size of medical landmark datasets impacts the effectiveness of…
"Multi-object tracking in videos requires to solve a fundamental problem of one-to-one assignment between objects in adjacent frames. Most methods address the problem by first discarding impossible pairs whose feature distances are larger than a threshold, followed by linking objects using Hungarian…
Gait recognition is a new biometric technology, which aims to identify people by their walking posture. Compared with fingerprint recognition, face recognition and other technologies, gait recognition usually has the characteristics of long-distance non-contact and difficulty in camouflage. And comp…
"While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform a systematic evaluation of the existing methods and find that they get notably larger errors when tested on different…
One of the most overlooked challenges in dance generation is that the auto-regressive frameworks are prone to freezing motions due to noise accumulation. In this paper, we present two modules that can be plugged into the existing models to enable them to generate non-freezing and high fidelity dance…
The state-of-the-art semi-supervised learning models are consistency-based which learn about unlabeled images by maximizing the similarity between different augmentations of an image. But when we apply the methods to human pose estimation which has extremely imbalanced class distribution, the models…
Estimating 3D human pose from a single image suffers from severe ambiguity since multiple 3D joint configurations may have the same 2D projection. The state-of-the-art methods often rely on context modeling methods such as pictorial structure model (PSM) or graph neural network (GNN) to reduce ambig…
Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning. Recent emergence of Transformer networks, which replace convolution layers with self-attention blocks, has revealed the limitation of stationary convolution kerne…
We propose to estimate 3D human pose from multi-view images and a few IMUs attached at person's limbs. It operates by firstly detecting 2D poses from the two signals, and then lifting them to the 3D space. We present a geometric approach to reinforce the visual features of each pair of joints based…
Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large num…
We present mph{VoxelPose} to estimate $3$D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete $2$D pose estimates, mph{VoxelPose} directly operates in the $3$D space therefore avo…
We present an approach to recover absolute 3D human poses from multi-view images by incorporating multi-view geometric priors in our model. It consists of two separate steps: (1) estimating the 2D poses in multi-view images and (2) recovering the 3D poses from the multi-view 2D poses. First, we intr…
A human pose is naturally represented as a graph where the joints are the nodes and the bones are the edges. So it is natural to apply Graph Convolutional Network (GCN) to estimate 3D poses from 2D poses. In this work, we propose a generic formulation where both GCN and Fully Connected Network (FCN)…
Archetypal analysis is an unsupervised learning approach which represents data by convex combinations of a set of archetypes. The archetypes generally correspond to the extremal points in the dataset and are learned by requiring them to be convex combinations of the training data. In spite of its ni…
We address the problem of video object segmentation which outputs the masks of a target object throughout a video given only a bounding box in the first frame. There are two main challenges for this task. First, the background may contain similar objects as the target. Second, the appearance of the…
Recognizing an action from a sequence of 3D skeletal poses is a challenging task. First, different actors may perform the same action in various performing styles. Second, the estimated poses are sometimes inaccurate due to sensory noises. These challenges can cause large variations between instance…